RESUMO
In the context of mobile health applications usability is a crucial factor to achieve user acceptance. The successful user interface (UI) design requires a deep understanding of the needs and requirements of the targeted audience. This paper explores the application of the K-Means algorithm on smartphone usage data in order to offer Human Computer Interaction (HCI) specialists a better insight into their user group. Two different feature space representations are introduced and used to identify persona like stereotypes in a real world data set, which was obtained from a public available smartphone application.
Assuntos
Telefone Celular/estatística & dados numéricos , Computadores de Mão/estatística & dados numéricos , Mineração de Dados/métodos , Sistemas Homem-Máquina , Monitorização Ambulatorial/estatística & dados numéricos , Telemedicina/instrumentação , Telemetria/estatística & dados numéricos , Diagnóstico por Computador/estatística & dados numéricosRESUMO
Purpose: Implanting stents to re-open stenotic lesions during percutaneous coronary interventions is considered a standard treatment for acute or chronic coronary syndrome. Intravascular ultrasound (IVUS) can be used to guide and assess the technical success of these interventions. Automatically segmenting stent struts in IVUS sequences improves workflow efficiency but is non-trivial due to a challenging image appearance entailing manifold ambiguities with other structures. Manual, ungated IVUS pullbacks constitute a challenge in this context. We propose a fully data-driven strategy to first longitudinally detect and subsequently segment stent struts in IVUS frames. Approach: A cascaded deep learning approach is presented. It first trains an encoder model to classify frames as "stent," "no stent," or "no use." A segmentation model then delineates stent struts on a pixel level only in frames with a stent label. The first stage of the cascade acts as a gateway to reduce the risk for false positives in the second stage, the segmentation, which is trained on a smaller and difficult-to-annotate dataset. Training of the classification and segmentation model was based on 49,888 and 1826 frames of 74 sequences from 35 patients, respectively. Results: The longitudinal classification yielded Dice scores of 92.96%, 82.35%, and 94.03% for the classes stent, no stent, and no use, respectively. The segmentation achieved a Dice score of 65.1% on the stent ground truth (intra-observer performance: 75.5%) and 43.5% on all frames (including frames without stent, with guidewires, calcium, or without clinical use). The latter improved to 49.5% when gating the frames by the classification decision and further increased to 57.4% with a heuristic on the plausible stent strut area. Conclusions: A data-driven strategy for segmenting stents in ungated, manual pullbacks was presented-the most common and practical scenario in the time-critical clinical workflow. We demonstrated a mitigated risk for ambiguities and false positive predictions.
RESUMO
Along with hibernating myocardium, infarct size is a critical term in the progression of left ventricular remodelling and congestive heart failure. Both infarcted and hibernating myocardium determine changes in remote non-ischaemic tissue. This study was designed to test the accuracy of a new technique to quantify infarct size using positron emission tomography (PET) with [18F]2-fluoro-2-deoxy-D-glucose (FDG). Studies were carried out in (a) nine pigs with acute myocardial infarction (two sham-operated), produced by a 90-min occlusion of the circumflex coronary artery followed by a 4-h reperfusion, and (b) humans (six patients with ischaemic cardiomyopathy awaiting cardiac transplantation and five normal volunteers). In both animals and patients, myocardial FDG uptake was measured by PET during hyperinsulinaemic-euglycaemic clamp. Infarct size was quantified by an absolute threshold of tracer uptake obtained from the parametric (voxel-by-voxel) image of the metabolic rate of FDG. PET infarct size estimates were compared with independent ex vivo planimetric measurements of the explanted swine and patient hearts (at transplantation) after staining with triphenyltetrazolium chloride. There was good agreement between the planimetric and PET infarct size estimates both in pigs (n=9; r=0.96, v=0.94x+0.64, SEE=0.10, P<0.0001) and in humans (n=11; r=0.94, y=0.72x+2.93, SEE=0.09, P<0.0001). This study demonstrates the feasibility and accuracy of this PET method in estimating infarct size both in a model of reperfused acute myocardial infarction and in chronic ischaemic cardiomyopathy, although larger studies are needed to confirm these findings.